/

Insights

Aug 1, 2022

Aug 1, 2022

Pieces User Stories: Keep track of machine learning papers

ML Engineer Patryk doesn’t spend a lot of time coding. But, Pieces is useful as he trains new ML models and researches solutions to challenging problems.

An illustration of Patryk.
An illustration of Patryk.
An illustration of Patryk.

Machine Learning Engineer Patryk doesn’t spend a lot of time coding; programming is actually a very small percentage of each of his tasks. But, Pieces has proved useful in his workflow as he trains new ML models and researches solutions to challenging problems.

“When it comes to an actual problem that I want to solve, before I come up with my own idea, I'm trying to figure out how people solve similar issues, and I'm trying to save all of the possible machine learning models that come out of that research. So, I’m saving the models to Pieces, comparing them later, and then coming up with my own idea or maybe just reusing some of the solutions that were used before.”

Patryk goes for quality over quantity when he saves snippets to his repo. “Because the problems that I'm solving are a task for a month or two, I don’t have that many snippets. But, all of them are very important.”

One of the features he uses most often is adding related links to his snippets. “I'll add webpages to Pieces because all of the machine learning models have papers. Then, this paper is related to the next paper which describes the whole method of how the model was designed. I assign all of these links to my model in Pieces, and then I can reference how it works. It’s just much easier.”

Pieces helps Patryk to ensure that all of his hard work pays off, saving him hours of work in the future. “The most useful snippet, for me, is not the one that I'm using the most, but the one that solves an important issue that I was thinking hard about before.”

SHARE

Pieces User Stories: Keep track of machine learning papers

Recent

Sep 17, 2025

Sep 17, 2025

Prototypes: the glue of Long-Term Memory

Explore how prototypes lay the foundation for long-term memory in AI. Learn why early experiments, iteration, and design “blueprints” are critical for building durable, context-rich intelligence.

Explore how prototypes lay the foundation for long-term memory in AI. Learn why early experiments, iteration, and design “blueprints” are critical for building durable, context-rich intelligence.

Sep 15, 2025

Sep 15, 2025

Why developers need AI that actually gets Their context

Tired of re-explaining your codebase to AI every week? Discover why developers need context-aware AI that remembers your workflow. Learn how Workstream Activity, Sources, and Time Ranges in Pieces give you control, continuity, and a searchable memory for your entire dev process.

Tired of re-explaining your codebase to AI every week? Discover why developers need context-aware AI that remembers your workflow. Learn how Workstream Activity, Sources, and Time Ranges in Pieces give you control, continuity, and a searchable memory for your entire dev process.

Sep 11, 2025

Sep 11, 2025

AI memory explained: what Perplexity, ChatGPT, Pieces, and Claude remember (and forget)

Discover the different types of AI memory, how they work, key use cases, and the best prompting approaches to get accurate, context-aware responses

Discover the different types of AI memory, how they work, key use cases, and the best prompting approaches to get accurate, context-aware responses

our newsletter

Sign up for The Pieces Post

Check out our monthly newsletter for curated tips & tricks, product updates, industry insights and more.

our newsletter

Sign up for The Pieces Post

Check out our monthly newsletter for curated tips & tricks, product updates, industry insights and more.

our newsletter

Sign up for The Pieces Post

Check out our monthly newsletter for curated tips & tricks, product updates, industry insights and more.